{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JLJ52YGN4JTI2JAAJ757ZAI2NY","short_pith_number":"pith:JLJ52YGN","canonical_record":{"source":{"id":"2410.13070","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T21:53:48Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"bc89933db02750e9b6f4a9f79aef1d43c05fc7ba198d5fd2d7d58915f83fbd55","abstract_canon_sha256":"19720bf5174767a54f519e4a3aa694f3598148d8c3b49386b85c62b8f46fb6a3"},"schema_version":"1.0"},"canonical_sha256":"4ad3dd60cde2668d24004ffbfc811a6e38f0bbd06b57a10ffa9a415e4b135871","source":{"kind":"arxiv","id":"2410.13070","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13070","created_at":"2026-07-05T09:21:54Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13070v1","created_at":"2026-07-05T09:21:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13070","created_at":"2026-07-05T09:21:54Z"},{"alias_kind":"pith_short_12","alias_value":"JLJ52YGN4JTI","created_at":"2026-07-05T09:21:54Z"},{"alias_kind":"pith_short_16","alias_value":"JLJ52YGN4JTI2JAA","created_at":"2026-07-05T09:21:54Z"},{"alias_kind":"pith_short_8","alias_value":"JLJ52YGN","created_at":"2026-07-05T09:21:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JLJ52YGN4JTI2JAAJ757ZAI2NY","target":"record","payload":{"canonical_record":{"source":{"id":"2410.13070","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T21:53:48Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"bc89933db02750e9b6f4a9f79aef1d43c05fc7ba198d5fd2d7d58915f83fbd55","abstract_canon_sha256":"19720bf5174767a54f519e4a3aa694f3598148d8c3b49386b85c62b8f46fb6a3"},"schema_version":"1.0"},"canonical_sha256":"4ad3dd60cde2668d24004ffbfc811a6e38f0bbd06b57a10ffa9a415e4b135871","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:54.866615Z","signature_b64":"jlVd7UKVad1n4NGhnlnpUtq4ZLd9bm0xVzzUlA6yNlf7bqNEVVw/M+oTm0ZogPkG85NZoHLWJg/ZTeen9uDkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ad3dd60cde2668d24004ffbfc811a6e38f0bbd06b57a10ffa9a415e4b135871","last_reissued_at":"2026-07-05T09:21:54.866131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:54.866131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.13070","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:21:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/DA550rIhzCmla4NpmcTuXmXotEWnpWC96hjVZZweuEEgQTnOidrs1qd/GGsJm8SlfEIZN6ksUYVjaizB9FNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:53:04.524847Z"},"content_sha256":"b49be5743110659384554176e15ee891b24d106016746723124b75ddd31a48b1","schema_version":"1.0","event_id":"sha256:b49be5743110659384554176e15ee891b24d106016746723124b75ddd31a48b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JLJ52YGN4JTI2JAAJ757ZAI2NY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is Semantic Chunking Worth the Computational Cost?","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Forrest Bao, Renyi Qu, Ruixuan Tu","submitted_at":"2024-10-16T21:53:48Z","abstract_excerpt":"Recent advances in Retrieval-Augmented Generation (RAG) systems have popularized semantic chunking, which aims to improve retrieval performance by dividing documents into semantically coherent segments. Despite its growing adoption, the actual benefits over simpler fixed-size chunking, where documents are split into consecutive, fixed-size segments, remain unclear. This study systematically evaluates the effectiveness of semantic chunking using three common retrieval-related tasks: document retrieval, evidence retrieval, and retrieval-based answer generation. The results show that the computat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13070","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.13070/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:21:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4UnAgFtH5/YVVzc0TgUfLtSAo7sRz/jhl3zfBv0KYuMt+d3SvrcTEmz1ygOm5O3CaRJa/7Hd3GD9R/DUk6aRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:53:04.525504Z"},"content_sha256":"9776edd63d3786b89980a45516c1c728cd8717657af01ddf956fd845db6b776a","schema_version":"1.0","event_id":"sha256:9776edd63d3786b89980a45516c1c728cd8717657af01ddf956fd845db6b776a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JLJ52YGN4JTI2JAAJ757ZAI2NY/bundle.json","state_url":"https://pith.science/pith/JLJ52YGN4JTI2JAAJ757ZAI2NY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JLJ52YGN4JTI2JAAJ757ZAI2NY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T05:53:04Z","links":{"resolver":"https://pith.science/pith/JLJ52YGN4JTI2JAAJ757ZAI2NY","bundle":"https://pith.science/pith/JLJ52YGN4JTI2JAAJ757ZAI2NY/bundle.json","state":"https://pith.science/pith/JLJ52YGN4JTI2JAAJ757ZAI2NY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JLJ52YGN4JTI2JAAJ757ZAI2NY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JLJ52YGN4JTI2JAAJ757ZAI2NY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"19720bf5174767a54f519e4a3aa694f3598148d8c3b49386b85c62b8f46fb6a3","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T21:53:48Z","title_canon_sha256":"bc89933db02750e9b6f4a9f79aef1d43c05fc7ba198d5fd2d7d58915f83fbd55"},"schema_version":"1.0","source":{"id":"2410.13070","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13070","created_at":"2026-07-05T09:21:54Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13070v1","created_at":"2026-07-05T09:21:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13070","created_at":"2026-07-05T09:21:54Z"},{"alias_kind":"pith_short_12","alias_value":"JLJ52YGN4JTI","created_at":"2026-07-05T09:21:54Z"},{"alias_kind":"pith_short_16","alias_value":"JLJ52YGN4JTI2JAA","created_at":"2026-07-05T09:21:54Z"},{"alias_kind":"pith_short_8","alias_value":"JLJ52YGN","created_at":"2026-07-05T09:21:54Z"}],"graph_snapshots":[{"event_id":"sha256:9776edd63d3786b89980a45516c1c728cd8717657af01ddf956fd845db6b776a","target":"graph","created_at":"2026-07-05T09:21:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.13070/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Retrieval-Augmented Generation (RAG) systems have popularized semantic chunking, which aims to improve retrieval performance by dividing documents into semantically coherent segments. Despite its growing adoption, the actual benefits over simpler fixed-size chunking, where documents are split into consecutive, fixed-size segments, remain unclear. This study systematically evaluates the effectiveness of semantic chunking using three common retrieval-related tasks: document retrieval, evidence retrieval, and retrieval-based answer generation. The results show that the computat","authors_text":"Forrest Bao, Renyi Qu, Ruixuan Tu","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T21:53:48Z","title":"Is Semantic Chunking Worth the Computational Cost?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13070","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b49be5743110659384554176e15ee891b24d106016746723124b75ddd31a48b1","target":"record","created_at":"2026-07-05T09:21:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"19720bf5174767a54f519e4a3aa694f3598148d8c3b49386b85c62b8f46fb6a3","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T21:53:48Z","title_canon_sha256":"bc89933db02750e9b6f4a9f79aef1d43c05fc7ba198d5fd2d7d58915f83fbd55"},"schema_version":"1.0","source":{"id":"2410.13070","kind":"arxiv","version":1}},"canonical_sha256":"4ad3dd60cde2668d24004ffbfc811a6e38f0bbd06b57a10ffa9a415e4b135871","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ad3dd60cde2668d24004ffbfc811a6e38f0bbd06b57a10ffa9a415e4b135871","first_computed_at":"2026-07-05T09:21:54.866131Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:54.866131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jlVd7UKVad1n4NGhnlnpUtq4ZLd9bm0xVzzUlA6yNlf7bqNEVVw/M+oTm0ZogPkG85NZoHLWJg/ZTeen9uDkAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:54.866615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13070","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b49be5743110659384554176e15ee891b24d106016746723124b75ddd31a48b1","sha256:9776edd63d3786b89980a45516c1c728cd8717657af01ddf956fd845db6b776a"],"state_sha256":"a48bb36d8e6e326dc1ca5bf18bc9ec5a2c04e6392e57535bb3c0c282d3158d91"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uDw9NLYXTZSPhUCGxERZLjnIAqG/x7NDGa6mQ3lysbiMeguRBRBKnCYpYJr4DarJNLlWsKmGRr5uei9exI1fAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:53:04.529573Z","bundle_sha256":"efaf2105fb56a0ce858da569f19414d812c7acc7a03c092eb1ba454a41542fc3"}}